Solving All Seismic Tomographic Problems using Deep Learning

In a variety of geoscientific applications scientists often need to image properties of the Earth's interior in order to understand the heterogeneity and processes taking place within the Earth. Seismic tomography is one such method which has been used widely to study properties of the subsurface. In order to solve tomographic problems efficiently, neural network-based methods have been introduced to geophysics. However, these methods can only be applied to certain types of problems with fixed acquisition geometry at a specific site. In this study we extend neural network-based methods to problems with various scales and acquisition geometries by using graph mixture density networks (MDNs). We train a graph MDN for 2D tomographic problems using simulated velocity models and travel time data, and apply the trained network to both synthetic and real data problems that have various scales and station distributions at different sites. The results demonstrate that graph MDNs can provide comparable solutions to those obtained using traditional Bayesian methods in seconds, and therefore provide the possibility to use graph MDNs to produce rapid solutions for all kinds of seismic tomographic problems over the world.